用tensorflow实现usps和mnist数据集的迁移学习
本程序环境：tensorflow+python，用到的库：numpy，os，Image，random。
基于论文：《Deep Transfer Network: Unsupervised Domain Adaptation》
前面我已经对这篇文章做过简单的导读：【深度学习】论文导读：无监督域适应（Deep Transfer Network: Unsupervised Domain Adaptation）
首先我们要用到两个数据集usps和mnist，它们都是用来完成手写数字识别任务的，以下提供两个数据集的下载链接
mnist数据集下载
usps数据集下载
上面两个链接下载下来，会发现mnist是以图片存储，而usps是以数值方式存储。这也是为了程序方便。
一.数据准备
首先需要读入usps数据集，因为usps是简单的以字符形式存储，所以读入也比较方便，程序如下，最后返回traindata矩阵以及trainlabel矩阵
def read_usps_dataset():
filename= '数据集文件路径'
fr = open(filename)
numberOfLines = len(fr.readlines())
traindataMat = zeros((numberOfLines,256)) #prepare matrix to return
trainlabelMat = zeros((numberOfLines),dtype=int32)
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip() #delete the /r/n
listFromLine = line.split(' ')
trainlabelMat[index] = listFromLine[0]
traindataMat[index, :] = float32(listFromLine[1:])
index += 1
print "the size of source dataset:",numberOfLines
trainlabelMat=array(trainlabelMat)
traindataMat=array(traindataMat)/float32(2)
trainlabelMat.astype(int)
return traindataMat,trainlabelMatdef preprocess_mnist():
image=[]
label=[]
i=0
for labels in range(10):
pathDir =os.listdir('MNIST/trainimage/pic2/'+str(labels)+'/')
for allDir in pathDir:
child = os.path.join('%s%s' % ('MNIST/trainimage/pic2/'+str(labels)+'/', allDir))
img = Image.open(child)
img=img.resize((16, 16))
img_array=array(img)
img_array=img_array[:,:,0]
img_array=reshape(img_array,-1)
image.append(img_array)
label.append(labels)
i=i+1
image = array(image)/float32(256)
label = array(label)
print "the size of target dataset:",i
return image,labeldef dense_to_one_hot(labels_dense, num_classes):
num_labels = labels_dense.shape[0]
index_offset = arange(num_labels) * num_classes
labels_one_hot = zeros((num_labels, num_classes))
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
return labels_one_hot二.创建M矩阵
M矩阵用于计算empirical Maximum Mean Discrepancy（MMD），我们一开始就要将它初始化
def createMmetrix():
mat1=tf.constant(float32(1)/(square(BATCHSIZE/2)),shape=[BATCHSIZE/2,BATCHSIZE/2],dtype=tf.float32)
mat2=-mat1
mat3=tf.concat(1,[mat1,mat2])
mat4=tf.concat(1,[mat2,mat1])
mat5=tf.concat(0,[mat3,mat4])
return mat5三.建立模型
采用两层卷积+全连接的结构，首先定义权值/偏置初始化函数，卷积/池化函数
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape = shape)
return tf.Variable(initial)
# convolution
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
# pooling
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')#first convolutinal layer
w_conv1 = weight_variable([3, 3, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(X, [-1, 16, 16, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# second convolutional layer
w_conv2 = weight_variable([3, 3, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# densely connected layer
w_fc1 = weight_variable([4*4*64, 256])
b_fc1 = bias_variable([256])
h_pool2_flat = tf.reshape(h_pool2, [-1, 4*4*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)
# softmax layer
w_fc2 = weight_variable([256, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1, w_fc2) + b_fc2)
obj_func= -tf.reduce_sum(Y * tf.log(y_conv))+tf.constant(lamda,dtype=tf.float32)*tf.trace(tf.matmul(tf.matmul(h_fc1,M,transpose_a=True),h_fc1))+tf.constant(miu,dtype=tf.float32)*tf.trace(tf.matmul(tf.matmul(y_conv,M,transpose_a=True),y_conv))
optimizer = tf.train.GradientDescentOptimizer(learningrate).minimize(obj_func)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))